avatar

Pin-Han (Hank) Huang

UCLA
pinhank@cs.ucla.edu

About Me

I am a first-year CS PhD student at UCLA, advised by Prof. Baharan Mirzasoleiman.

Previously, I have obtained my Bachelor’s degree in Computer Science from National Taiwan University in August 2025. During my studies, I’ve had the pleasure of collaborating with Prof. Shang-Tse Chen and Prof. Hsuan-Tien Lin. I was also a visiting student at the University of Waterloo working with Prof. Freda Shi.

Research

  1. Expanding the Role of Diffusion Models for Robust Classifier Training NeurIPS
    Expanding the Role of Diffusion Models for Robust Classifier Training
    Pin-Han Huang, Shang-Tse Chen†, Hsuan-Tien Lin†
    NeurIPS 2026
    PDF Code
  2. Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss ICML
    Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
    Bo-Han Lai*, Pin-Han Huang*, Bo-Han Kung*, Shang-Tse Chen
    ICML 2025 · Spotlight
    arXiv Code OpenReview Project Page
*Equal Contribution   †Co-advisors